Building intelligent autonomous systems at any scale is challenging. The sensing and computation constraints of a microrobot platform make the problems harder. We present improvements to learning-based methods for on-board learning of locomotion, classification, and navigation of microrobots. We show how simulated locomotion can be achieved with model-based reinforcement learning via on-board sensor data distilled into control. Next, we introduce a sparse, linear detector and a Dynamic Thresholding method to FAST Visual Odometry for improved navigation in the noisy regime of mm scale imagery. We end with a new image classifier capable of classification with fewer than one million multiply-and-accumulate (MAC) operations by combining fast downsampling, efficient layer structures and hard activation functions. These are promising steps toward using state-of-the-art algorithms in the power-limited world of edge-intelligence and microrobots.
Real-time autonomous magnetic microrobot navigation across dynamic and biologically relevant environments
Department of Mechanical Engineering, University of Delaware（德克萨斯大学机械工程系）；Department of Animal and Food Sciences, University of Delaware（德克萨斯大学动物与食品科学系）；School of Civil and Environmental Engineering, Cornell University（康奈尔大学土木与环境工程学院）
Planning locomotion trajectories for legged microrobots is challenging because of their complex morphology, high frequency passive dynamics, and discontinuous contact interactions with their environment. Consequently, such research is often driven by time-consuming experimental methods. As an alternative, we present a framework for systematically modeling, planning, and controlling legged microrobots. We develop a three-dimensional dynamic model of a 1.5 gram quadrupedal microrobot with complexity (e.g., number of degrees of freedom) similar to larger-scale legged robots. We then adapt a recen…
Indian Institute of Technology Kharagpur（印度理工学院卡拉格普尔分校）
On the lines of the huge and varied efforts in the field of automation with respect to technology development and innovation of vehicles to make them run autonomously, this paper presents an innovation to a bicycle. A normal daily use bicycle was modified at low cost such that it runs autonomously, while maintaining its original form i.e. the manual drive. Hence, a bicycle which could be normally driven by any human and with a press of switch could run autonomously according to the needs of the user has been developed.
Wyss Institute for Biologically Inspired Engineering（怀斯生物启发工程研究所）
Limitations in actuation, sensing, and computation have forced small legged robots to rely on carefully tuned, mechanically mediated leg trajectories for effective locomotion. Recent advances in manufacturing, however, have enabled the development of small legged robots capable of operation at multiple stride frequencies using multi-degree-of-freedom leg trajectories. Proprioceptive sensing and control is key to extending the capabilities of these robots to a broad range of operating conditions. In this work, we use concomitant sensing for piezoelectric actuation with a computationally efficie…
Due to the highly complex environment present during the DARPA Subterranean Challenge, all six funded teams relied on legged robots as part of their robotic team. Their unique locomotion skills of being able to step over obstacles require special considerations for navigation planning. In this work, we present and examine ArtPlanner, the navigation planner used by team CERBERUS during the Finals. It is based on a sampling-based method that determines valid poses with a reachability abstraction and uses learned foothold scores to restrict areas considered safe for stepping. The resulting planni…
Learning Robust Autonomous Navigation and Locomotion for Wheeled-Legged Robots
Robotic Systems Lab, ETH Zurich（苏黎世联邦理工学院机器人系统实验室）；Neuromeka；Swiss-Mile Robotics AG（Swiss-Mile机器人公司）；The work was carried out during their stay at（该工作是在他们停留期间完成的）
The Hong Kong Polytechnic University（香港理工大学）；The Chinese University of Hong Kong（香港中文大学）；Shenzhen Loop Area Institute（深圳河套学院）；Harbin Institute of Technology（哈尔滨工业大学）
The design of gaits for robot locomotion can be a daunting process which requires significant expert knowledge and engineering. This process is even more challenging for robots that do not have an accurate physical model, such as compliant or micro-scale robots. Data-driven gait optimization provides an automated alternative to analytical gait design. In this paper, we propose a novel approach to efficiently learn a wide range of locomotion tasks with walking robots. This approach formalizes locomotion as a contextual policy search task to collect data, and subsequently uses that data to learn…
Learning to Evolve: Multi-modal Interactive Fields for Robust Humanoid Navigation in Dynamic Environments
State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School（一般人工智能国家重点实验室，北京大学深圳研究生院）；Oxford Robotics Institute, University of Oxford（牛津大学机器人研究所）；Institute for Machine Learning, Department of Computer Science, ETH Zurich（苏黎世联邦理工学院计算机科学系机器学习研究所）
Microrobots are considered as promising tools for biomedical applications. However, the imaging of them becomes challenges in order to be further applied on in vivo environments. Here we report the magnetic navigation of a paramagnetic nanoparticle based swarm using ultrasound images. The swarm can be generated using simple rotating magnetic fields, resulting in a region containing particles with a high area density. Ultrasound images of the swarm shows a periodic changing of imaging contrast. The reason for such dynamic contrast has been analyzed and experimental results are presented. Moreov…
Rectilinear forms of snake-like robotic locomotion are anticipated to be an advantage in obstacle-strewn scenarios characterizing urban disaster zones, subterranean collapses, and other natural environments. The elongated, laterally-narrow footprint associated with these motion strategies is well-suited to traversal of confined spaces and narrow pathways. Navigation and path planning in the absence of global sensing, however, remains a pivotal challenge to be addressed prior to practical deployment of these robotic mechanisms. Several challenges related to visual processing and localization ne…
Co-training with Ego-centric Video and Demonstration for Robot Navigation Task
Department of Informatics, Graduate School of Informatics, Kyoto University（信息学系，京都大学研究生院）；Spatial Robotics Research Center, Fujitsu Limited（空间机器人研究中心，富士通有限公司）
Reinforcement Learning with Data Bootstrapping for Dynamic Subgoal Pursuit in Humanoid Robot Navigation
Mechanical and Aerospace Engineering, The Ohio State University（机械与航空航天工程，俄亥俄州立大学）；Electrical and Computer Engineering, The Ohio State University（电气与计算机工程，俄亥俄州立大学）；Computer Science and Engineering, The Ohio State University（计算机科学与工程，俄亥俄州立大学）
Towards Path-Creative Navigation: Robot Navigation through Embodied Interaction
School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机科学学院）；College of Information Science and Technology, Eastern Institute of Technology（东方理工大学信息科学与技术学院）；School of Mechanical and Power Engineering, Zhengzhou university（郑州大学机械与动力工程学院）；University of Waterloo（滑铁卢大学）
Continuous robot operation in extreme scenarios such as underground mines or sewers is difficult because exteroceptive sensors may fail due to fog, darkness, dirt or malfunction. So as to enable autonomous navigation in these kinds of situations, we have developed a type of proprioceptive localization which exploits the foot contacts made by a quadruped robot to localize against a prior map of an environment, without the help of any camera or LIDAR sensor. The proposed method enables the robot to accurately re-localize itself after making a sequence of contact events over a terrain feature. Th…
Harvard University（哈佛大学）；University of Colorado Boulder（科罗拉多大学博尔德分校）；Wyss Institute for Biologically Inspired Engineering（怀斯生物启发工程研究所）
Here we present HAMR-Jr, a \SI{22.5}{\milli\meter}, \SI{320}{\milli\gram} quadrupedal microrobot. With eight independently actuated degrees of freedom, HAMR-Jr is, to our knowledge, the most mechanically dexterous legged robot at its scale and is capable of high-speed locomotion (\SI{13.91}{bodylengths~\second^{-1}}) at a variety of stride frequencies (\SI{1}{}-\SI{200}{\hertz}) using multiple gaits. We achieved this using a design and fabrication process that is flexible, allowing scaling with minimum changes to our workflow. We further characterized HAMR-Jr's open-loop locomotion and compare…
Gait learning for soft microrobots controlled by light fields
Micro, Nano, and Molecular Systems Group, Max Planck Institute for Intelligent Systems（微、纳、分子系统组，人工智能系统马克斯·普朗克研究所）；Max Planck ETH Center for Learning Systems（马克斯·普朗克-ETH学习系统中心）
Analysis of the navigation of magnetic microrobots through cerebral bifurcations
Porto University（波尔图大学）；Experian（益博睿）；Magnebotix；ETH Zurich（苏黎世联邦理工学院）；University of Thessaly（色萨利大学）；University of Barcelona（巴塞罗那大学）；Institució Catalana de Recerca i Estudis Avançats (ICREA)（加泰罗尼亚研究与高级研究机构）
UC Berkeley（加州大学伯克利分校）；Facebook AI Research（Facebook人工智能研究院）；Technion（以色列理工学院）；OpenAI
We introduce a new memory architecture, Bayesian Relational Memory (BRM), to improve the generalization ability for semantic visual navigation agents in unseen environments, where an agent is given a semantic target to navigate towards. BRM takes the form of a probabilistic relation graph over semantic entities (e.g., room types), which allows (1) capturing the layout prior from training environments, i.e., prior knowledge, (2) estimating posterior layout at test time, i.e., memory update, and (3) efficient planning for navigation, altogether. We develop a BRM agent consisting of a BRM module …
Perceiving the surrounding environment is crucial for autonomous mobile robots. An elevation map provides a memory-efficient and simple yet powerful geometric representation for ground robots. The robots can use this information for navigation in an unknown environment or perceptive locomotion control over rough terrain. Depending on the application, various post processing steps may be incorporated, such as smoothing, inpainting or plane segmentation. In this work, we present an elevation mapping pipeline leveraging GPU for fast and efficient processing with additional features both for navig…
Generating natural and physically feasible motions for legged robots has been a challenging problem due to its complex dynamics. In this work, we introduce a novel learning-based framework of autoregressive motion planner (ARMP) for quadruped locomotion and navigation. Our method can generate motion plans with an arbitrary length in an autoregressive fashion, unlike most offline trajectory optimization algorithms for a fixed trajectory length. To this end, we first construct the motion library by solving a dense set of trajectory optimization problems for diverse scenarios and parameter settin…
This study proposes an integrated task and motion planning method for dynamic locomotion in partially observable environments with multi-level safety guarantees. This layered planning framework is composed of a high-level symbolic task planner and a low-level phase-space motion planner. A belief abstraction at the task planning level enables belief estimation of dynamic obstacle locations and guarantees navigation safety with collision avoidance. The high-level task planner, i.e., a two-level navigation planner, employs linear temporal logic for a reactive game synthesis between the robot and …
Understanding and following directions provided by humans can enable robots to navigate effectively in unknown situations. We present FollowNet, an end-to-end differentiable neural architecture for learning multi-modal navigation policies. FollowNet maps natural language instructions as well as visual and depth inputs to locomotion primitives. FollowNet processes instructions using an attention mechanism conditioned on its visual and depth input to focus on the relevant parts of the command while performing the navigation task. Deep reinforcement learning (RL) a sparse reward learns simultaneo…
Clinically Ready Magnetic Microrobots for Targeted Therapies
Magnebotix AG（Magnebotix公司）；University of Würzburg（维尔茨堡大学）；University of Thessaly（色萨利大学）；University of Barcelona（巴塞罗那大学）；Institució Catalana de Recerca i Estudis Avançats (ICREA)（加泰罗尼亚研究与高等教育学院）；Porto University（波尔图大学）；Fudan University（复旦大学）；Yiwu Research Institute of Fudan University（复旦大学义乌研究院）；University Hospital of Zurich（苏黎世大学医院）；University of Zurich（苏黎世大学）；University Children's Hospital Zurich（苏黎世大学儿童医院）；Kantonsspital Aarau AG（阿尔高州立医院）；University Hospital Zurich（苏黎世大学医院）
Gallant: Voxel Grid-based Humanoid Locomotion and Local-navigation across 3D Constrained Terrains
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）；University of Science and Technology of China（中国科学技术大学）；University of Tokyo（东京大学）；Shanghai Jiaotong University（上海交通大学）
Institute of Robotics and Intelligent Manufacturing (IRIM), The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）机器人与智能制造研究院（IRIM））；Shenzhen Institute of Artificial Intelligence and Robotics for Society (AIRS), The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）深圳人工智能与机器人研究院（AIRS））
Quadruped locomotion is currently a vibrant research area, which has reached a level of maturity and performance that enables some of the most advanced real-world applications with autonomous quadruped robots both in academia and industry. Blind robust quadruped locomotion has been pushed forward in control and technology aspects within recent decades. However, in the complicated environment, the capability including terrain perception and path planning is still required. Visual perception is an indispensable ability in legged locomotion for such a demand. This study explores a vision-based na…
TRANS: Terrain-aware Reinforcement Learning for Agile Navigation of Quadruped Robots under Social Interactions
Department of Robotics, Graduate School of Engineering, Tohoku University（东邦大学机器人学系）；Laboratory for Intelligent Decision and Autonomous Robots, Woodruff School of Mechanical Engineering, Georgia Institute of Technology（佐治亚理工学院智能决策与自主机器人实验室）
The common approach for local navigation on challenging environments with legged robots requires path planning, path following and locomotion, which usually requires a locomotion control policy that accurately tracks a commanded velocity. However, by breaking down the navigation problem into these sub-tasks, we limit the robot's capabilities since the individual tasks do not consider the full solution space. In this work, we propose to solve the complete problem by training an end-to-end policy with deep reinforcement learning. Instead of continuously tracking a precomputed path, the robot nee…
Hierarchical Experience-informed Navigation for Multi-modal Quadrupedal Rebar Grid Traversal
Georgia Institute of Technology（佐治亚理工学院）；School of Mechanical Engineering, Georgia Institute of Technology（佐治亚理工学院机械工程学院）；SkyMul Inc（SkyMul公司）；School of Electrical and Computer Engineering, Georgia Institute of Technology（佐治亚理工学院电气与计算机工程学院）
End-to-End Humanoid Robot Safe and Comfortable Locomotion Policy
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；The Hong Kong University of Science and Technology（香港科技大学）；Human-Robot Interfaces and Interaction Lab., Istituto Italiano di Tecnologia, Italy（人机交互实验室，意大利理工学院）
Zhejiang University（浙江大学）；Huzhou Institute, Zhejiang University（浙江大学湖州研究院）；Harbin Institute of Technology（哈尔滨工业大学）
Terrestrial-aerial bimodal vehicles bloom in both academia and industry because they incorporate both the high mobility of aerial vehicles and the long endurance of ground vehicles. In this work, we present an autonomous and adaptive navigation framework to bring complete autonomy to this class of vehicles. The framework mainly includes 1) a hierarchical motion planner that generates safe and low-power terrestrial-aerial trajectories in unknown environments and 2) a unified motion controller which dynamically adjusts energy consumption in terrestrial locomotion. Extensive real-world experiment…
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Vanderbilt University（范德堡大学）
We tackle the problem of perceptive locomotion in dynamic environments. In this problem, a quadrupedal robot must exhibit robust and agile walking behaviors in response to environmental clutter and moving obstacles. We present a hierarchical learning framework, named PRELUDE, which decomposes the problem of perceptive locomotion into high-level decision-making to predict navigation commands and low-level gait generation to realize the target commands. In this framework, we train the high-level navigation controller with imitation learning on human demonstrations collected on a steerable cart a…
